AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Multi-dimensional Neural Decoding with Orthogonal Representations for Brain-Computer Interfaces

Kaixi Tian, Shengjia Zhao, Yuhan Zhang, Shan Yu

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add OrthoSchema (orthogonal loss + session head + selective transfer) to RNN backboneRNN · CO cross-session 2-shotDirection accuracy (%): 72.60 -> 80.23Improved
add OrthoSchema to CNN backboneCNN · CO cross-session 5-shotHand acceleration R2: 0.562 -> 0.550Hurt
add OrthoSchema to RNN backboneRNN · CO cross-subject 2-shotDirection accuracy (%): 45.53 -> 60.01Improved
add OrthoSchema to RNN backboneRNN · CO to RT cross-paradigm 2-shotPosition R2: 0.579 -> 0.622Improved
add OrthoSchema to MLP backboneMLP · CO cross-session 5-shotDirection accuracy (%): 94.02 -> 94.39No clear effect
add OrthoSchema to MLP backboneMLP · CO to RT cross-paradigm 5-shotPosition R2: 0.618 -> 0.624No clear effect
add orthogonal loss to base multi-task RNN (ablation)RNN · CO cross-session 2-shotDirection accuracy: about +6%Improved
add session classification head to base multi-task RNN (ablation)RNN · CO cross-session 2-shotDirection accuracy: about +2%Improved
combine orthogonal loss and session head (full method) vs base (ablation)RNN · CO cross-session 2-shotDirection accuracy: about +8%Improved
vary orthogonal loss weight (0.001-0.005 or 0.1-0.5 vs 0.05) (ablation)OrthoSchema RNN · CO cross-session 2-shotDirection accuracyMixed
vary transfer feature retention ratio (10-20% or 50-100% vs 30%) (ablation)OrthoSchema RNN · CO cross-session 2-shotDirection accuracyMixed
add OrthoSchema vs multi-task baselines (UW, GradNorm) and neural decoders (LFADS, NoMAD)RNN · CO cross-session 2-shotDirection accuracy (%): 67.74 (NoMAD) -> 80.23Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy